{"id":"W4406171015","doi":"10.1109/tase.2025.3527327","title":"Behaviorally-Aware Multi-Agent RL With Dynamic Optimization for Autonomous Driving","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Autonomous agent; Vehicle dynamics; Control engineering; Engineering; Artificial intelligence; Automotive engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002782453,0.0001206203,0.00009590693,0.0004679048,0.0003823834,0.0003227669,0.0003026976,0.00003853668,0.000002590746],"category_scores_gemma":[0.00001339559,0.000115948,0.00002397516,0.0008712506,0.00005294733,0.0009301476,0.000004567111,0.00009473001,0.000001966978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002045164,"about_ca_system_score_gemma":0.0001484396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002963389,"about_ca_topic_score_gemma":0.000002933089,"domain_scores_codex":[0.9990282,0.00000613165,0.0001807932,0.0002999497,0.000260541,0.0002243762],"domain_scores_gemma":[0.9994357,0.00004969877,0.00004859902,0.0002373803,0.0001676539,0.00006099257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.924073e-7,0.00001483596,0.000007715691,0.00002038513,0.000004695924,3.334257e-7,0.0001710162,0.9842026,0.001157763,0.000197903,0.000001690113,0.01422002],"study_design_scores_gemma":[0.0002905743,0.00006183994,0.0008048497,0.00007662392,0.00001172264,0.000003311403,0.00002717303,0.9960453,0.002508919,0.000001602207,0.00004129243,0.0001268016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005846279,0.000004376216,0.9927868,0.0001946874,0.0004295189,0.0003002954,9.544073e-7,0.0004195257,0.00001759736],"genre_scores_gemma":[0.7442443,0.000005622099,0.2555105,0.0000386896,0.000002285777,0.00005673144,7.744109e-7,0.000006204878,0.0001348338],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.738398,"threshold_uncertainty_score":0.4728222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01107059958361727,"score_gpt":0.2564603295386846,"score_spread":0.2453897299550673,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}